Peptide Manufacturability Scoring for Synthesis and Solubility Risk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing peptide manufacturing processes face challenges in accurately predicting the manufacturability of peptides due to factors such as peptide length, sequence, pH, temperature, and storage conditions, leading to significant manufacturing failures.
Innovation Solution
A computer-based algorithm using machine learning models assesses manufacturability by evaluating synthesizability, solubility, and quality control of peptides through a hierarchical model, incorporating features like amino acid composition, solvent compatibility, and mass spectrometry data to predict manufacturability scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional peptide manufacturing processes are used, then peptides can be synthesized, but a substantial percentage of peptides fail to be properly synthesized due to factors like peptide length, sequence, pH, temperature, and storage conditions
Solution Approach 1:
The patent applies preliminary action by using machine learning models to predict peptide manufacturability before the actual manufacturing process begins. The system evaluates multiple factors including peptide length, amino acid sequence, pH conditions, temperature, and storage conditions in advance to identify peptides that are likely to fail synthesis. This allows manufacturers to screen out problematic peptides before investing resources in their synthesis, thereby improving the overall manufacturing success rate while managing process complexity through computational prediction.
2Measurement precision
If machine learning models are used to predict manufacturability, then prediction accuracy improves, but the complexity of the manufacturing system increases
Solution Approach 1:
The patent employs an intermediary approach by introducing machine learning models as a separate prediction layer that mediates between the peptide design stage and the manufacturing stage. The ML models take peptide sequence and structural features as input and output manufacturability predictions, acting as an intermediary filter. This allows the manufacturing system to maintain its core functions while gaining predictive capabilities through a modular addition that doesn't fundamentally alter the manufacturing process itself, thus improving prediction accuracy while managing system complexity through clear separation of concerns.
Data Source
AI summary
Approaches for predicting manufacturability of a peptide are provided. A request for information related to manufacturability of a peptide can be received. A determination as to whether the peptide is predicted to be synthesizable can be made, such as by using a machine learning model. The machine learning model can be trained on data including manufacturer specifications and descriptions associated with a peptide and features for peptides. A second determination can be made as to whether the peptide is predicted to be soluble, using the same or different machine learning model trained with solubility data for peptides. If the peptide is predicted to be soluble and synthesizable, a manufacturability score for the peptide can be determined. The manufacturability score can correspond to or be indicative of a chance of successfully manufacturing the peptide.